arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1807.01604stat.MLcs.LG
收藏

拟蒙特卡罗变分推断

Quasi-Monte Carlo Variational Inference

ENSAE-CREST;TU Kaiserslautern(凯泽斯劳滕工业大学)

Alexander Buchholz, Florian Wenzel, Stephan Mandt

摘要:

许多机器学习问题涉及蒙特卡罗梯度估计。作为一个突出的例子,我们集中在蒙特卡罗变分推断(MCVI)在本文中。MCVI的性能关键取决于其随机梯度的方差。本文提出了利用准蒙特卡罗(QMC)抽样的方差缩减方法. QMC取代N i.i.d.通过长度为N的确定性样本序列从均匀概率分布中提取样本。这个序列比i.i.d.更均匀地覆盖了底层的随机变量空间。绘制,减少梯度估计器的方差。与我们的新方法,无论是得分函数和重新参数化梯度估计导致更快的收敛。我们还提出了一个新的算法,蒙特卡罗目标,在那里我们操作一个恒定的学习率,并增加每次迭代的QMC样本的数量。我们证明,这样,我们的算法可以渐近收敛速度比SGD。此外,我们提供了理论保证QMC的蒙特卡罗目标,超越MCVI,并支持我们的研究结果,从不同领域的大规模数据集上的几个实验。

英文摘要:

Many machine learning problems involve Monte Carlo gradient estimators. As a prominent example, we focus on Monte Carlo variational inference (MCVI) in this paper. The performance of MCVI crucially depends on the variance of its stochastic gradients. We propose variance reduction by means of Quasi-Monte Carlo (QMC) sampling. QMC replaces N i.i.d. samples from a uniform probability distribution by a deterministic sequence of samples of length N. This sequence covers the underlying random variable space more evenly than i.i.d. draws, reducing the variance of the gradient estimator. With our novel approach, both the score function and the reparameterization gradient estimators lead to much faster convergence. We also propose a new algorithm for Monte Carlo objectives, where we operate with a constant learning rate and increase the number of QMC samples per iteration. We prove that this way, our algorithm can converge asymptotically at a faster rate than SGD. We furthermore provide theoretical guarantees on QMC for Monte Carlo objectives that go beyond MCVI, and support our findings by several experiments on large-scale data sets from various domains.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑